Non-photorealistic neural sketching

Author:

de Arruda Francisco de Assis Pereira Vasconce,de Queiroz José Eustáquio Rangel,Gomes Herman Martins

Abstract

Abstract We present and evaluate a neural network-based technique to automatically enable NPR renderings from digital face images, which resemble semi-detailed sketches. The technique has been experimentally evaluated and compared with traditional approaches to edge detection (Canny and Difference of Gaussians, or DoG) and with a more recent variant, specifically designed for stylization purposes (Flow Difference of Gaussians, or FDoG). An objective evaluation showed, after an ANOVA analysis and a Tukey t-test, that the proposed approach was equivalent to the FDoG technique and superior to the DoG. A subjective experiment involving the opinion of human observers proved to be complementary to the objective analysis.

Publisher

Springer Science and Business Media LLC

Subject

General Computer Science

Reference72 articles.

1. Arruda FA, Porto VA, Gomes HM, de Queiroz JER, Moroney N (2007) Facial sketching based on sub-image illumination removal and multiscale edge filtering. In: Proc IEEE SITIS 2007. IEEE Comp Soc, Los Alamitos, pp 520–527

2. Barile P, Ciesielski V, Trist K (2008) Non-photorealistic rendering using genetic programming. In: Proc 7th int conf on sim evolution and learning, vol 5361. Springer, Berlin, pp 299–308

3. Barnard K, Funt B (1999) Investigations into multi-scale retinex. In: Color imaging in multimedia. Wiley, New York, pp 9–17

4. Barnard K, Cardei V, Funt B (2002) A comparison of computational color constancy algorithms. IEEE Trans Image Process 11(9):972–984

5. Becerikli Y, Demiray HE, Ayhan M, Aktas K (2006) Alternative neural network based edge detection. Neural Inf Process – Lett Rev 10:193–199

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3